Brain tumor is the third-most common cause of cancer related deaths in the world. Fortunately, it can be detected using MRI. Computer-aided diagnosis (CADx) systems can help clinicians identify cancer from brain diseases more accurately. In this project, propose a CAD system that distinguishes and classifies brain tumor from pre-cancerous conditions. The system uses a deplearning model. Deep CNN which involves depth wise separable convolutions, to classify cancer and non-cancers.
The proposed method consist of two steps:
Google’s Auto Augment for augmentation and the CV2 based feature selection for image segmentation during pre- processing. These approaches produce a feasible methods of distinguishing and classifying cancers from other brain diseases. Our methods are fully automated without the manual specification of region-of-interests for the test and with a random selection of images for model training. This methodology may play a crucial role in selecting effective treatment options without the need for a surgical biopsy.